I
Imran Saleemi
Researcher at University of Central Florida
Publications - 21
Citations - 1934
Imran Saleemi is an academic researcher from University of Central Florida. The author has contributed to research in topics: Object detection & Optical flow. The author has an hindex of 14, co-authored 21 publications receiving 1611 citations.
Papers
More filters
Proceedings ArticleDOI
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
TL;DR: This work relies on multiple sources such as low confidence head detections, repetition of texture elements, and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region, and employs a global consistency constraint on counts using Markov Random Field.
Journal ArticleDOI
Probabilistic Modeling of Scene Dynamics for Applications in Visual Surveillance
TL;DR: A novel method to model and learn the scene activity, observed by a static camera, in the form of a multivariate nonparametric probability density function of spatiotemporal variables is proposed, useful for activity analysis applications, such as persistent tracking and anomalous motion detection.
Proceedings ArticleDOI
Scene understanding by statistical modeling of motion patterns
TL;DR: A novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera, and an algorithm for learning these patterns from dense optical flow in a hierarchical, unsupervised fashion.
Journal ArticleDOI
Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions
TL;DR: The completely unsupervised proposed representation of articulated human actions and gestures and facial expressions, in contrast to state-of-the-art representations like bag of video words, provides a meaningful representation conducive to visual interpretation and textual labeling.
Journal ArticleDOI
Multimodal Analysis for Identification and Segmentation of Moving-Sounding Objects
TL;DR: A novel method that exploits correlation between audio-visual dynamics of a video to segment and localize objects that are the dominant source of audio to solve the problem of audio-video synchronization and is used to aid interactive segmentation.